One Transit Is All You Need: Detecting Exoplanets Through Learned Stellar Behaviour with EXOVEIL
arXiv:2606.02778v1 Announce Type: cross Abstract: I present EXOVEIL, a transit detection system that learns what a star's brightness should look like and flags when reality disagrees. Unlike existing systems that require phase-folded input, EXOVEIL operates on raw flux time series and can detect planets that transit only once.A Transformer world model, trained on 16,499 Kepler light curves with transit-masked self-supervised learning, predicts expected stellar flux. A matched-filter detector with variance weighting extracts transit signals from the prediction residuals. A learned classifier (X
The proliferation of advanced AI models like Transformers, coupled with increasing computational power, allows for sophisticated pattern recognition in astronomical data that was previously infeasible.
This development significantly enhances our ability to detect exoplanets, especially those that transit infrequently, potentially revolutionizing exoplanet discovery and characterization, which informs our understanding of planetary systems beyond our own.
The reliance on phase-folded light curves for exoplanet detection is reduced, enabling the discovery of planets from single transit events and expanding the scope of observable exoplanetary systems.
- · Astrophysicists
- · Space agencies
- · AI researchers
- · Observatories
- · Traditional exoplanet detection methods
Increased rate of exoplanet discovery and validation, particularly for long-period or single-transit planets.
Revision of exoplanet population statistics and improved models of planetary formation and evolution.
Enhanced prospects for identifying potentially habitable exoplanets and informing future remote sensing missions.
This signal links to a primary source. Continuum Brief monitors and indexes it as part of the live intelligence stream — we do not republish source content.
Read at arXiv cs.LG